Creatures: Entertainment Software Agents with Artificial Life

被引：1
作者：
Grand S. [1 ]
Cliff D. [2 ]
机构：
[1] CyberLife Technology Ltd, Cambridge CB5 8AB, Quayside, Bridge Street
[2] Artificial Intelligence Laboratory, Massachusetts Inst. of Technology, Cambridge, MA 02139
来源：
Autonomous Agents and Multi-Agent Systems | 1998年 / 1卷 / 1期
关键词：
Adaptive behavior; Artificial life; Entertainment software; Evolutionary computation;
D O I：
10.1023/A:1010042522104
中图分类号：
学科分类号：
摘要：
We present a technical description of Creatures, a commercial home-entertainment software package. Creatures provides a simulated environment in which exist a number of synthetic agents that a user can interact with in real-time. The agents (known as "creatures") are intended as sophisticated "virtual pets". The internal architecture of the creatures is strongly inspired by animal biology. Each creature has a neural network responsible for sensory-motor coordination and behavior selection, and an "artificial biochemistry" that models a simple energy metabolism along with a "hormonal" system that interacts with the neural network to model diffuse modulation of neuronal activity and staged ontogenetic development. A biologically inspired learning mechanism allows the neural network to adapt during the lifetime of a creature. Learning includes the ability to acquire a simple verb-object language. Additionally, both the network architecture and details of the biochemistry for a creature are specified by a variable-length "genetic" encoding, allowing for evolutionary adaptation through sexual reproduction. Creatures, available on Windows95 platforms since late 1996, offers users an opportunity to engage with Artificial Life technologies. In addition to describing technical details, this paper concludes with a discussion of the scientific implications of the system.
引用
收藏
页码：39 / 57
页数：18
相关论文
共 37 条
  • [1] Anark, (1996)
  • [2] Arbib M.A., The Handbook of Brain Theory and Neural Networks, (1995)
  • [3] Bates J., The role of emotion in believable characters, Communications of the ACM, 37, 7, (1994)
  • [4] Beer R.D., On the Dynamics of Small Continuous-Time Recurrent Neural Networks, Adaptive Behavior, 3, 4, pp. 471-511, (1995)
  • [5] Beer R.D., A Dynamical Systems Perspective on agent-environment interaction, Artificial Intelligence, 72, pp. 173-215, (1995)
  • [6] Beer R.D., Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior, (1996)
  • [7] Blumberg B., Action Selection in Hamsterdam: Lessons from Ethology, (1994)
  • [8] Blumberg B., Old Tricks, New Dogs: Ethology and Interactive Creatures, pp. 108-117, (1996)
  • [9] Boden M., The Philosophy of Artificial Life, (1996)
  • [10] Brooks R., Maes P., ALifeIV: Proceedings of the Artificial Life IV Workshop, (1994)
1234